© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2999
    Prev
    Next
    INDEX
    Explanations

    pulling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.64
    CodedInputStream
    -0.56
     بيها
    -0.51
    Salle
    -0.47
     scorso
    -0.46
     chi̍t
    -0.45
     ivelany
    -0.43
    addContainerGap
    -0.43
     तह
    -0.43
     مشين
    -0.43
    POSITIVE LOGITS
    TypedDataSet
    0.63
    twimg
    0.56
    cadores
    0.52
     Franco
    0.52
     serializers
    0.51
    setVerticalGroup
    0.51
    enschappelijke
    0.51
    NameValuePair
    0.50
    raised
    0.50
    nhi
    0.50
    Activations Density 0.001%

    No Known Activations